© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34758
    Prev
    Next
    INDEX
    Explanations

    case distinctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assertion
    0.42
    StripMenuItem
    0.38
    ведена
    0.38
    correctAns
    0.37
     svom
    0.37
     denomina
    0.36
    ጎ
    0.35
     Assertion
    0.35
    ÇA
    0.35
     করিতে
    0.35
    POSITIVE LOGITS
     Cancel
    0.40
     பகிர்ந்து
    0.39
     Rolling
    0.38
     gluten
    0.38
    gluten
    0.38
     bundle
    0.38
    //
    0.37
    乐队
    0.37
    Justin
    0.36
     Musicians
    0.36
    Activations Density 0.000%

    No Known Activations